Multi-thread parallel algorithm for reconstructing 3D large-scale porous structures. (April 2017)

• Record Type: Journal Article
• Authors: Ju, Yang; Huang, Yaohui; Zheng, Jiangtao; Qian, Xu; Xie, Heping; Zhao, Xi
• Is Part Of: Computers & geosciences. Volume 101(2017)
• Page Start: 10
• Page End: 20
• Publication Date: 2017-04
• Subjects: 3D reconstruction -- Porous structure -- Multi-thread parallel reconstruction algorithm -- Large scale -- Fractal characterization -- Pre-conditioning method; Environmental policy -- Periodicals; 550.5
• DOI: 10.1016/j.cageo.2017.01.003
• Languages: English
• ISSNs: 0098-3004

Abstract

Abstract: Geomaterials inherently contain many discontinuous, multi-scale, geometrically irregular pores, forming a complex porous structure that governs their mechanical and transport properties. The development of an efficient reconstruction method for representing porous structures can significantly contribute toward providing a better understanding of the governing effects of porous structures on the properties of porous materials. In order to improve the efficiency of reconstructing large-scale porous structures, a multi-thread parallel scheme was incorporated into the simulated annealing reconstruction method. In the method, four correlation functions, which include the two-point probability function, the linear-path functions for the pore phase and the solid phase, and the fractal system function for the solid phase, were employed for better reproduction of the complex well-connected porous structures. In addition, a random sphere packing method and a self-developed pre-conditioning method were incorporated to cast the initial reconstructed model and select independent interchanging pairs for parallel multi-thread calculation, respectively. The accuracy of the proposed algorithm was evaluated by examining the similarity between the reconstructed structure and a prototype in terms of their geometrical, topological, and mechanical properties. Comparisons of the reconstruction efficiency of porous models with various scales indicated that the parallel multi-thread scheme significantly shortened the execution time for reconstruction of a large-scale well-connected porous model compared to a sequential single-thread procedure. Highlights: A novel method was developed to reconstruct the pore structures of geomaterials. A multi-threads parallel scheme was proposed to improve reconstruction efficiency. Four correlation functions were used for better representation of 3D structures. The reconstructed models and the reference one showed good agreement. Parallel computing greatly shortened the reconstruction time of large-scale models.